Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to "ide" or "ideological" terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ideologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.98
    iona
    -0.92
    ichick
    -0.87
    ufact
    -0.76
    é¾
    -0.71
    thening
    -0.71
    wagen
    -0.71
    cffff
    -0.69
    itton
    -0.69
    lishing
    -0.68
    POSITIVE LOGITS
    gger
    0.97
    maid
    0.90
    ously
    0.88
    lli
    0.88
    ll
    0.86
    lla
    0.79
    llo
    0.78
    creen
    0.76
    hare
    0.73
     Dhabi
    0.72
    Act Density 0.031%

    No Known Activations